Crop Recommender System Using Machine Learning Approach and IoT
Smitha N1, Dr. Ravindra P Rajput2
1Student, Dept. of Electronics and Communication Engineering, University BDT College of Engineering, Karnataka, India.
2Professor & Chairman, Dept. of Electronics and Communication Engineering, University BDT College of Engineering, Karnataka, India.
----------------------------------------------------------------***--------------------------------------------------------------
Abstract – Food, shelter and clothing are essential for human survival. With advancements in science and technology, we’ve seen incredible improvements in the way we design and build modern homes and clothing. From smart homes that use various technologies to make our lives more comfortable and convenient, to high fabrics that provide better insulation and protection, we’re living in the era of incredible innovation and progress. With increased awareness and support, we can create a more inclusive and diverse community in agriculture. However, there are initiatives and programs in place to provide education and training for farmers to improve their knowledge and skills. These programs can cover topics such as crop management, soil health, pest control, and sustainable farming practices, which can help farmers, increase their yields, reduce their environmental impact, and improve their livelihoods. Additionally, there are also scientific advancements in agriculture technology that aim to simplify and automate farming processes, making it easier for farmers to manage their crops and minimize errors. By leveraging technology and data-driven models, we can help farmers make more informed decisions and reduce the need for trial and error. This can save time and resources for farmers, leading to more efficient and sustainable farming practices. By providing farmers with the right tools and information, we can help improve their livelihoods and contribute to the overall growth and prosperity of the agricultural sector.
Keywords: Machine Learning, ESP32 microcontroller, DHT 11 sensor, K-Nearest Neighbours (KNN)
